AutoML Leaderboard

Best model	name	model_type	metric_type	metric_value	train_time
	1_Baseline	Baseline	auc	0.5	0.94
	2_DecisionTree	Decision Tree	auc	0.510386	7.38
	3_Linear	Linear	auc	0.595857	4.48
	4_Default_Xgboost	Xgboost	auc	0.583604	33.93
	5_Default_NeuralNetwork	Neural Network	auc	0.541889	3.16
	6_Default_RandomForest	Random Forest	auc	0.567825	11.46
the best	Ensemble	Ensemble	auc	0.59864	0.52

AutoML Performance

AutoML Performance Boxplot

Features Importance

Spearman Correlation of Models

Summary of 5_Default_NeuralNetwork

<< Go back

Neural Network

• n_jobs: -1
• dense_1_size: 32
• dense_2_size: 16
• learning_rate: 0.05
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

2.3 seconds

Metric details

	score	threshold
logloss	0.808877	nan
auc	0.541889	nan
f1	0.660714	0.000300195
accuracy	0.540667	0.495761
precision	0.603448	0.850206
recall	1	0.000300195
mcc	0.0848235	0.495761

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.808877	nan
auc	0.541889	nan
f1	0.573902	0.495761
accuracy	0.540667	0.495761
precision	0.529076	0.495761
recall	0.627027	0.495761
mcc	0.0848235	0.495761

Confusion matrix (at threshold=0.495761)

	Predicted as 0	Predicted as 1
Labeled as 0	347	413
Labeled as 1	276	464

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back

Summary of 1_Baseline

<< Go back

Baseline Classifier (Baseline)

• n_jobs: -1
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

0.3 seconds

Metric details

	score	threshold
logloss	0.693059	nan
auc	0.5	nan
f1	0.660714	0.4436
accuracy	0.493333	0.4436
precision	0.493333	0.4436
recall	1	0.4436
mcc	0	0.4436

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.693059	nan
auc	0.5	nan
f1	0.660714	0.4436
accuracy	0.493333	0.4436
precision	0.493333	0.4436
recall	1	0.4436
mcc	0	0.4436

Confusion matrix (at threshold=0.4436)

	Predicted as 0	Predicted as 1
Labeled as 0	0	760
Labeled as 1	0	740

Learning curves

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back

Summary of Ensemble

<< Go back

Ensemble structure

Model	Weight
3_Linear	2
4_Default_Xgboost	1

Metric details

	score	threshold
logloss	0.682195	nan
auc	0.59864	nan
f1	0.661239	0.239071
accuracy	0.582667	0.499564
precision	0.763158	0.733148
recall	1	0.106754
mcc	0.165128	0.499564

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.682195	nan
auc	0.59864	nan
f1	0.575881	0.499564
accuracy	0.582667	0.499564
precision	0.577446	0.499564
recall	0.574324	0.499564
mcc	0.165128	0.499564

Confusion matrix (at threshold=0.499564)

	Predicted as 0	Predicted as 1
Labeled as 0	449	311
Labeled as 1	315	425

Learning curves

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back

Summary of 2_DecisionTree

<< Go back

Decision Tree

• n_jobs: -1
• criterion: gini
• max_depth: 3
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

6.4 seconds

Metric details

	score	threshold
logloss	0.698446	nan
auc	0.510386	nan
f1	0.660714	0.228814
accuracy	0.513333	0.551724
precision	0.590909	0.665424
recall	1	0.228814
mcc	0.0307276	0.551724

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.698446	nan
auc	0.510386	nan
f1	0.126794	0.551724
accuracy	0.513333	0.551724
precision	0.552083	0.551724
recall	0.0716216	0.551724
mcc	0.0307276	0.551724

Confusion matrix (at threshold=0.551724)

	Predicted as 0	Predicted as 1
Labeled as 0	717	43
Labeled as 1	687	53

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back

Summary of 6_Default_RandomForest

<< Go back

Random Forest

• n_jobs: -1
• criterion: gini
• max_features: 0.9
• min_samples_split: 30
• max_depth: 4
• eval_metric_name: auc
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

10.5 seconds

Metric details

	score	threshold
logloss	0.687506	nan
auc	0.567825	nan
f1	0.663307	0.443609
accuracy	0.552	0.489128
precision	0.635417	0.53655
recall	1	0.362554
mcc	0.105715	0.489128

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.687506	nan
auc	0.567825	nan
f1	0.569231	0.489128
accuracy	0.552	0.489128
precision	0.541463	0.489128
recall	0.6	0.489128
mcc	0.105715	0.489128

Confusion matrix (at threshold=0.489128)

	Predicted as 0	Predicted as 1
Labeled as 0	384	376
Labeled as 1	296	444

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back

Summary of 4_Default_Xgboost

<< Go back

Extreme Gradient Boosting (Xgboost)

• n_jobs: -1
• objective: binary:logistic
• eta: 0.075
• max_depth: 6
• min_child_weight: 1
• subsample: 1.0
• colsample_bytree: 1.0
• eval_metric: auc
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

33.0 seconds

Metric details

	score	threshold
logloss	0.691952	nan
auc	0.583604	nan
f1	0.660714	0.0736868
accuracy	0.577333	0.510962
precision	0.65	0.764196
recall	1	0.0736868
mcc	0.154109	0.510962

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.691952	nan
auc	0.583604	nan
f1	0.553521	0.510962
accuracy	0.577333	0.510962
precision	0.577941	0.510962
recall	0.531081	0.510962
mcc	0.154109	0.510962

Confusion matrix (at threshold=0.510962)

	Predicted as 0	Predicted as 1
Labeled as 0	473	287
Labeled as 1	347	393

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back

Summary of 3_Linear

<< Go back

Logistic Regression (Linear)

• n_jobs: -1
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

3.5 seconds

Metric details

	score	threshold
logloss	0.686974	nan
auc	0.595857	nan
f1	0.660714	0.0801389
accuracy	0.576	0.492873
precision	0.675	0.717623
recall	1	0.0801389
mcc	0.152125	0.492873

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.686974	nan
auc	0.595857	nan
f1	0.574866	0.492873
accuracy	0.576	0.492873
precision	0.568783	0.492873
recall	0.581081	0.492873
mcc	0.152125	0.492873

Confusion matrix (at threshold=0.492873)

	Predicted as 0	Predicted as 1
Labeled as 0	434	326
Labeled as 1	310	430

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back